Feasibility of an Intelligent Home-Based Neurorehabilitation System for Upper Extremity Mobility Assessment

Abstract

Health personnel are often unavailable for supervised robot-aided neurorehabilitation in hospitals, and patients are usually challenged by transportation issues to get to hospital. Thus, a discontinuity between therapy in hospital and at home appears slowing down the upper extremity mobility recovery. The aim of this work was to develop a system, based on wearable devices and EMG armband, able to assess the quality of the upper extremity joint movements and intelligently guide the patients during a home-based rehabilitation. This system fuses a classification model together with a dynamic time warping analysis. The classification model was trained with upper extremity joint movements gathered from clinicians, obtaining more than 80% of accuracy using only five joint angles. Then, the system was tested in two post-stroke patients and a healthy subject. The results suggest that the proposed system can be: (i) a useful tool for clinicians to evaluate the rehabilitation therapy; and (ii) an intelligent system able to make decision based on the quality of the activity executed at home.